Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
- python == 3.7.13
- cudatoolkit == 10.1.243
- pytorch ==1.7.1
- torchvision == 0.8.2
- numpy, scikit-learn, PIL, argparse
- Configure the PyTorch environment.
- Download the Office-Home dataset. Configure the data lists in data and the checkpoints in ckpts.
- Run the code in ensv.sh.
@inproceedings{hu2024towards,
title={Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline},
author={Dapeng Hu and Mi Luo and Jian Liang and Chuan-Sheng Foo},
booktitle={The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2024}
}